Loading video...

Video Failed to Load

Go Home

Deterministic inference: getting the exact same output every time you run an LLM with identical inputs. Try it yourself: Powered by EigenAI

29,352 views • 1 year ago •via X (Twitter)

20 Comments

nader dabit's profile picture
nader dabit1 year ago

Why it matters:

binji's profile picture
binji1 year ago

@eigencloud you guy are killing it on this front wow

nader dabit's profile picture
nader dabit1 year ago

@eigencloud thank you, this has been really fun to work with, 100% credit goes to engineering team I just get to go out and build with + talk about it 😅

EigenCloud's profile picture
EigenCloud1 year ago

this changes how we build, not just how we prompt big up! 🫡🔥

Beebs's profile picture
Beebs1 year ago

@eigencloud Is it just caching the response? What if it hallucinates when doing a certain tool call? It will be broken in prod for a given input until changing the seed?

WillisYang's profile picture
WillisYang1 year ago

@eigencloud Huge props to the engineering team and to you for bringing it to life

Deus Machina's profile picture
Deus Machina1 year ago

@eigencloud @dabit3 Please check this out It has multiple code repositories, documentation , blogs indexed in it , so you literally asked anything .

Renvik | Web3 Activist 💵's profile picture
Renvik | Web3 Activist 💵1 year ago

@eigencloud This is huge — deterministic outputs make debugging, testing, and verifiable AI much more feasible. Definitely worth trying! ⚡🤖

KullGurl's profile picture
KullGurl1 year ago

@eigencloud wait wtf no more bullshit variance? trying rn

Defi Brew's profile picture
Defi Brew1 year ago

@eigencloud Can you put the output back in and return the input ?

Vaibhav Maheshwari's profile picture
Vaibhav Maheshwari1 year ago

@eigencloud what a breakthrough, truly!!

loveabit's profile picture
loveabit1 year ago

@eigencloud 🚀 Consistent results every time! Great for reliable AI interactions. Check out powered by EigenAI. #LLM #AI

Ninja_Dev's profile picture
Ninja_Dev1 year ago

@eigencloud Ok what is this sorcery. I'm am intrigued. You mean my LLM will not tell lies when asked the same question?!?!

Max's profile picture
Max1 year ago

@eigencloud Verifiable inference More details

Zoir's profile picture
Zoir1 year ago

@eigencloud This could save hours of debugging, trying it now

ghøst's profile picture
ghøst1 year ago

@eigencloud Teach me...

Deep Sage's profile picture
Deep Sage1 year ago

@eigencloud Is it self hosted or using open ai apis ?

Jeycosmos ⚔️'s profile picture
Jeycosmos ⚔️1 year ago

@eigencloud this could be a total vibe check for lllm reliability, right?

Zoir's profile picture
Zoir1 year ago

@eigencloud Finally something to calm my hyperparameter anxiety, trying it now

Rohit's profile picture
Rohit1 year ago

@eigencloud This is very interesting. I'm building a mobile app using AI and one of the challenges I'm working through is determinism. Will give this a shot

Related Videos